AI Engineer

We're looking for a talented and motivated individual to join our team as an AI Engineer. In this role, you'll have the opportunity to work on cutting-edge projects that combine generative AI, agentic systems, machine learning (ML), Large Language Models (LLMs), and prompt engineering to drive innovation. You'll be responsible for designing, developing, and deploying complex solutions in distributed and cloud environments, working with large datasets and text-based data to create innovative technical solutions. 

This role is fully remote.  On an exception basis may be required to come in once a quarter for planning purposes to Washington, DC.

Responsibilities: 

• Build and deploy agentic AI systems capable of autonomous decision-making, tool use, and multi-step task execution 

• Implement end-to-end AI/ML and GenAI projects, from understanding business needs to data preparation, model development, deployment and monitoring 

• Develop LLM-based features such as retrieval-augmented generation (RAG) with citations, text summarization, and embedding pipelines 

• Design and optimize prompts using prompt engineering techniques for LLMs to achieve desired outcomes 

• Work with Large Language Models (LLMs) such as Claude, GPT, Gemini, Llama, etc. via APIs or cloud AI platforms to develop solutions for specific tasks 

• Evaluate and test GenAI features: building test sets, grounding and citation checks, LLM-as-judge scoring, and production quality monitoring 

• Design, develop, and optimize machine learning models using Python 

• Deploy and manage solutions in distributed and cloud environments 

• Collaborate with cross-functional teams to guide business decisions 

Job Requirements: 

• Bachelor's/Master's degree in CS, Data Science, Engineering, or Mathematics field 

• 2+ years of hands-on AI/ML engineering experience, including demonstrable LLM application work 

• Experience building agentic AI systems (agents with tool/function calling, planning or task decomposition, and multi-step execution), or strong working knowledge of agent architectures and frameworks such as LangGraph, CrewAI, Strands, or AutoGen 

• Working knowledge of the modern LLM stack: prompt engineering, RAG, embeddings, and structured outputs 

• Experience in one or more areas of machine learning / artificial intelligence such as classification, clustering, anomaly detection, sentiment analysis, and NLP problems such as text categorization, topic modeling, entity extraction, and text summarization 

• Ability to think critically about AI or ML system design, including model selection, tradeoffs, and real-world deployment considerations 

• Experience evaluating AI/ML systems: testing, measuring accuracy, and catching hallucinations 

• Programming experience using Python and iPython notebooks; good SQL skills 

• Excellent communication skills to communicate with wide technical and business users 

• Demonstrate ability to quickly learn new tools and paradigms to deploy cutting edge solutions 

• Adept at simultaneously working on multiple projects, meeting deadlines, and managing expectations 

Preferred Skills: 

• Experience with prompt engineering techniques such as few-shot learning, zero-shot learning, and chain-of-thought prompting 

• Experience with cloud platforms (AWS or Azure) and their AI/ML services such as AWS Bedrock, AWS SageMaker, Azure OpenAI, or Azure AI Foundry, and core services such as S3 and Lambda functions 

• Experience in using deep learning frameworks such as PyTorch or Keras, etc. 

• Experience in MLOps to operationalize the model building process and monitor models in production 

• Familiarity with search and vector retrieval such as Elasticsearch, Solr, or vector databases 

• Familiarity with version control systems, specifically Git, and experience with platforms like Azure DevOps 

• Familiarity with Linux and cloud CLI tools 

• Experience creating interactive data visualizations and dashboards in Tableau, Power BI, or other tools 

• Experience with distributed NoSQL databases such as MongoDB, DynamoDB, etc. 

• Ability to build full stack systems architected for speed and distributed computing